Electric power engineering safety learning platform course resource intelligent recommendation method and system

Abstract

The invention provides an electric power engineering safety learning platform course resource intelligent recommendation method and system, and relates to the technical field of learning platforms. The method comprises the following steps: acquiring student information; establishing association between the student information and element nodes in a pre-constructed structured association system; according to the corresponding nodes associated with the trainee, identifying a safety knowledge point set associated with the trainee by traversing an association path in the structured association system; according to the dynamic information of the student, adjusting the recommendation priority of the course resource associated with the safety knowledge point set to obtain the adjusted recommendation priority; and according to the adjusted recommendation priority, screening and sorting the course resources, and generating a recommendation list and pushing the recommendation list to the student. Compared with a traditional mode, the method can recognize personalized safe learning requirements and weak links of students more accurately and more timely, dynamically recommend most relevant courses, and greatly improve the pertinence and effectiveness of learning.

Description

Technical Field

[0001] The present invention relates to the technical field of learning platforms, and in particular to a method and system for intelligently recommending course resources for a power engineering safety learning platform. Background Art

[0002] Safety in the power industry is crucial. Power companies are widely developing power engineering safety learning platforms to enhance employee safety skills and awareness. These platforms offer a wide range of safety training courses, including procedures, operational demonstrations, accident case studies, and emergency drills. After logging in, students will learn relevant safety knowledge related to their job roles.

[0003] The power engineering field offers a wide variety of job roles, and safety requirements vary widely. Line inspectors need to master safety in height work, electric shock prevention, and fieldwork risk avoidance, while substation operators must be familiar with substation equipment operation, switching safety, and fire and explosion prevention.

[0004] Learning platforms offer a vast array of courses. Facing this vast amount of resources, students face the challenge of quickly and accurately locating the content most relevant to their roles and most urgently needed. Traditionally, students manually search or browse course catalogs based on job titles, which is inefficient and prone to missing key courses. Even when platforms offer course listings categorized by job title, these categorizations are often too coarse to meet students' refined learning needs.

[0005] The actual safety knowledge required by trainees depends not only on the job title but also on a variety of underlying factors, such as job responsibilities, equipment type, operating environment, and regional safety regulations. The trainee's career development stage also influences their choice of learning content. New trainees need to systematically study basic theory, general safety procedures, and basic operating specifications; experienced trainees may need to learn advanced safety knowledge specific to complex equipment or high-risk operating scenarios; and experienced expert trainees may need to focus on the latest technological developments, accident prevention, or participate in safety management courses.

[0006] Power industry safety regulations, national standards, and internal company regulations are constantly changing, and students must stay up-to-date on the latest regulations relevant to their roles. When regulations or standards change, the platform identifies which roles and students' learning content are affected and proactively recommends updated courses or supplemental learning materials.

[0007] A student's personal learning history and performance are also crucial for assessing their safety knowledge and identifying weaknesses. Their learning history on the platform, online assessment scores, feedback on safety issues encountered in their work, and knowledge points related to similar historical incidents all reflect their current knowledge and potential safety risks.

[0008] Existing power engineering safety learning platforms often struggle to effectively integrate this multi-dimensional, dynamically changing information when recommending course resources, making it impossible to provide personalized, dynamic, and precise course resource recommendations for each student. This mismatch in information can lead students to spend time studying courses that are not highly relevant to their current work, while missing out on key courses that are most closely related to their job responsibilities, actual working environment, experience level, and the latest safety requirements, and that can best enhance their safety skills. This mismatch in learning resources not only impacts learning efficiency and motivation, but more importantly, may fail to address students' safety knowledge blind spots in specific areas in a timely manner, creating potential safety hazards and undermining safe production in the power industry. Summary of the Invention

[0009] The purpose of the present invention is to provide a method and system for intelligently recommending course resources for an electric power engineering safety learning platform. By constructing a structured knowledge system and combining it with students' multi-dimensional dynamic information for association and priority adjustment, the method and system can identify students' personalized safety learning needs and weaknesses more accurately and timely than traditional methods, and dynamically recommend the most relevant courses, greatly improving the pertinence and effectiveness of learning.

[0010] In a first aspect, the present invention provides a method for intelligently recommending course resources on a power engineering safety learning platform, comprising the following steps: Collect student information; student information includes student dynamic information; Establish associations between student information and element nodes in a pre-built structured association system; the structured association system includes multiple element nodes related to power safety and association paths formed by connecting different element nodes according to specific association relationships; According to the corresponding nodes associated with the students, the set of safety knowledge points related to the students is identified by traversing the association paths in the structured association system; According to the dynamic information of the students, the recommendation priority of the course resources associated with the security knowledge point set is adjusted to obtain the adjusted recommendation priority; Based on the adjusted recommendation priority, the course resources are filtered and sorted, and a recommendation list is generated and pushed to the students.

[0011] The method for intelligently recommending course resources for an electric power engineering safety learning platform provided by the present invention establishes precise and dynamic associations between students' individual safety knowledge needs and massive course resources in the electric power engineering safety learning platform based on multi-dimensional information such as students' positions, working environments, equipment types, learning histories, assessment performances, and dynamically changing regulations and accident cases. Based on this, the method intelligently recommends the most relevant courses to address personalized and dynamic learning needs that cannot be met by traditional simple matching methods.

[0012] In a second aspect, the present invention provides an intelligent recommendation system for course resources on a power engineering safety learning platform, comprising: The collection module is used to collect student information; student information includes student dynamic information; The association module is used to associate student information with element nodes in a pre-built structured association system; the structured association system includes multiple power safety-related element nodes and association paths formed by connecting different element nodes according to specific association relationships; The identification module is used to identify the set of safety knowledge points related to the student by traversing the association path in the structured association system based on the corresponding nodes associated with the student; An adjustment module, configured to adjust the recommendation priority of course resources associated with the security knowledge point set according to the dynamic information of the students, and obtain an adjusted recommendation priority; The generation module is used to filter and sort course resources according to the adjusted recommendation priority, generate a recommendation list and push it to students.

[0013] As can be seen from the above, the intelligent course resource recommendation method for the power engineering safety learning platform provided by this invention establishes a structured association system that reflects the inherent logical relationships in the field of power engineering safety. This system comprises multiple power safety-related element nodes and their specific associations. Students' dynamic information (such as learning history, assessment scores, associated procedural changes, and relevant accident cases) is mapped to corresponding nodes in this system. By traversing the association paths in the system, the set of safety knowledge points most relevant to the student's current status and needs is determined. Based on these knowledge points, courses are then filtered, sorted, and recommended from the course resource library.

[0014] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flowchart of a method for intelligently recommending course resources on a power engineering safety learning platform provided by an embodiment of the present invention.

[0016] Figure 2 A structural diagram of an intelligent recommendation system for course resources on a power engineering safety learning platform provided by an embodiment of the present invention.

[0017] Description of labels: 100, acquisition module; 200, association module; 300, identification module; 400, adjustment module; 500, generation module. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0019] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0020] Reference Attachment Figure 1 The present invention provides an intelligent recommendation method for course resources of an electric power engineering safety learning platform, comprising the following steps: Collect student information; student information includes static attribute information and dynamic information of students; Establish associations between student information and element nodes in a pre-built structured association system; the structured association system includes multiple element nodes related to power safety and association paths formed by connecting different element nodes according to specific association relationships; According to the corresponding nodes associated with the students, the set of safety knowledge points related to the students is identified by traversing the association paths in the structured association system; According to the dynamic information of the students, the recommendation priority of the course resources associated with the security knowledge point set is adjusted to obtain the adjusted recommendation priority; Based on the adjusted recommendation priority, the course resources are filtered and sorted, and a recommendation list is generated and pushed to the students.

[0021] Student information refers to data used to describe a student's individual characteristics and behaviors. It includes both static and dynamic information about the student. Static information can be represented by relatively stable data such as the student's position, department, length of service, and educational background. Its primary purpose is to provide a basic student profile. Dynamic information can be represented by data that changes over time, such as the student's learning history, test scores, browsing behavior, search keywords, and feedback on problems encountered in actual work. It primarily reflects the student's current learning status, knowledge acquisition, and actual needs.

[0022] A structured association system is a pre-built knowledge network used to organize and associate power safety-related knowledge and elements. It includes multiple power safety-related element nodes and association paths formed by connecting these elements according to specific relationships. Element nodes can be implemented as nodes representing concepts such as safety knowledge points, procedures, equipment, positions, accident cases, and work environments. Association paths can be implemented using edges representing semantic relationships such as "belongs to," "related to," "involved," and "needs to be understood." The primary purpose of this system is to construct a system that reflects the complex knowledge structure of the power safety field and facilitates association discovery and reasoning.

[0023] Associating student information with element nodes in a pre-built structured association system means connecting individual students to one or more element nodes in the structured association system, thereby placing the students within the knowledge system. This association can be achieved by directly matching student attributes with node labels, such as associating a student's position with a position node in the system; it can also be achieved by parsing student behavior data and mapping it to relevant nodes, such as associating the course content viewed by students with knowledge point nodes in the system. The main purpose is to match the individual characteristics and behaviors of students with the specific content of the power safety knowledge system, laying the foundation for subsequent knowledge discovery.

[0024] Traversing the association paths within a structured association system refers to the process of exploring and accessing other element nodes along different types of associations within the system, starting from the element node associated with the trainee. This process can be implemented using graph traversal algorithms, such as depth-first search or breadth-first search, and can be guided by pre-set strategies (such as the priority of different association types and node weights) to determine the direction and depth of the traversal. The primary goal is to discover security knowledge points or other relevant elements that are directly or indirectly related to the trainee and hidden within complex associations.

[0025] Adjusting the recommendation priority of course resources associated with a set of safety knowledge points based on students' dynamic information means, after identifying the safety knowledge points relevant to the students, using the students' latest behavior and status data to modify the recommendation order or weight of the course resources corresponding to these knowledge points. This adjustment can be achieved by calculating an impact factor based on dynamic information such as the students' recent learning behavior, exam performance, and feedback on actual problems, and applying it to the basic recommendation score of the course resources. This is primarily intended to ensure that the recommendation results can promptly reflect the students' most urgent learning needs, weaknesses, or concerns, thereby improving the timeliness and accuracy of the recommendations.

[0026] The working principle of this application is to first construct a knowledge graph in the field of power engineering safety, which contains various safety-related entities (such as positions, tasks, risks, procedures, knowledge points, equipment, environment, accidents, and courses) and predefined relationships between them. The system then collects students' static information (such as positions, equipment, and environment) and dynamic information (such as learning progress, exam scores, procedure updates, and incidents) and associates this information with corresponding entity nodes in the knowledge graph. When recommending courses for students, the system starts from the student's associated node and traverses the associated paths in the graph to preliminarily identify the set of relevant safety knowledge points. The system then dynamically adjusts the recommendation priority of these knowledge points and their associated courses based on the student's learning history, assessment performance, and association with procedure changes and incident cases. Finally, based on the adjusted priority, the system selects and sorts the courses from the course resource library that best suit the student's current needs and presents them to the student. This process is dynamic and adjusts in real time as the student's status and external information (such as procedures and incidents) change.

[0027] The core innovation of this application lies in that it deeply integrates students' multi-dimensional information (including static attributes and dynamic behaviors) with a pre-built structured power safety knowledge association system, and conducts intelligent association discovery and dynamic recommendation priority adjustment based on this system, thereby solving the problem in existing technologies that it is difficult to effectively integrate multi-dimensional and dynamically changing information for personalized and precise course recommendations, thereby achieving the effect of improving the pertinence, timeliness and effectiveness of recommendations, and better meeting students' personalized learning needs.

[0028] Specifically, the solution of this application constructs a comprehensive student profile by collecting both static and dynamic information about the student. This student information is then associated with element nodes in a pre-built structured association system, mapping the individual student to the power safety knowledge network. Based on the student's associated nodes in the system, the association paths within the structured association system are traversed to systematically identify a set of safety knowledge points relevant to the student. This process leverages the structure and associations of the knowledge system to uncover potential, indirectly related knowledge needs of the student. After identifying relevant safety knowledge points, the system then retrieves course resources associated with these knowledge points. Key to this is the use of dynamic student information, such as recent learning progress, knowledge gaps exposed in exams, and new challenges encountered in real-world work, to dynamically adjust the recommendation priority of these course resources. This adjustment ensures that the recommended courses promptly address the student's most pressing needs or weakest areas. Finally, based on the dynamically adjusted recommendation priorities, the course resources are screened and ranked, generating a personalized recommendation list that is then pushed to the student. The entire process forms a closed loop, starting from student information, conducting in-depth mining through the knowledge system, and then combining dynamic information for real-time optimization, ultimately achieving accurate and timely course resource push.

[0029] The constructed structured association system for power engineering safety knowledge can be stored and managed using a graph database. Node types (such as "position," "assignment," "safety risk," "knowledge point," and "course resource") represent entities in the graph, while association types (such as "responsibility," "exists," "corresponds," "includes," and "explained on") represent edges. After student information is collected, connections are established between students and corresponding nodes in the graph database. For example, student "Zhang San" is associated with the "high-voltage electrician" node, the "mountainous environment" node, and the "tower equipment" node. To identify Zhang San's safety knowledge needs, the system performs a graph traversal query starting from the node associated with Zhang San (such as "high-voltage electrician"). For example, the query path can be set as follows: starting from the "position" node, following the "responsibility" relationship to the "assignment" node, then following the "exists" relationship to the "safety risk" node, then following the "corresponds" relationship to the "regulations and provisions" node, and finally following the "includes" relationship to the "knowledge point" node. At the same time, it is also possible to follow the "involved" relationship from the "job task" node to the "equipment type" or "work environment" node, and then continue to traverse the relevant paths from these nodes to reach the knowledge points. The graph database query engine performs traversal operations based on the set traversal rules and the starting node associated with the student, collects all the "knowledge point" nodes reached, and forms a set of safety knowledge points related to Zhang San. For example, the traversal results may include knowledge points such as "high-altitude work safety", "correct use of safety belts", "prevention of electric shock", "risk avoidance of field work in mountainous areas", and "tower structure safety".

[0030] As a preferred embodiment, the solution of this application is specifically implemented as follows: a student information database can be established to store static attributes such as the student's position, department, length of service, and other static attributes, as well as dynamic behavioral data such as the student's browsing history, learning time, test scores, and course completion status on the learning platform. At the same time, an electric power safety knowledge graph is constructed as a structured association system, in which nodes can include specific safety regulations, equipment models, operating procedures, accident types, risk points, job titles, etc., and edges can represent various associations between these elements, such as "Position A requires mastery of regulation B", "Operation of equipment C involves step D", and "Accident E is related to risk point F". When a student logs in to the platform, the system first reads its static attributes and recent dynamic information from the database. Then, the student's position information is associated with the position node in the knowledge graph, and the course content that the student recently browsed or studied is associated with the knowledge point node in the graph. Next, starting from these associated nodes, the system traverses the knowledge graph according to pre-set traversal rules (for example, prioritizing "need to master" relationships over "related to" relationships), identifying a set of safety knowledge points related to the trainee's job responsibilities and recent learning content. For example, if the trainee is a substation operator, the system will traverse knowledge points such as substation equipment operation and switching operation safety. If the trainee recently took a course on a specific piece of equipment, the system will further traverse knowledge points such as the detailed operating procedures for that equipment and related accident cases. After identifying the set of knowledge points, the system searches for course resources related to these knowledge points. It also analyzes the trainee's dynamic information, such as a low score on a recent switching operation simulation exam or feedback submitted by the trainee regarding a problem with a particular piece of equipment. Based on this dynamic information, the system prioritizes recommended course resources related to switching operation and the equipment in question. For example, courses on switching operation safety procedures and demonstration videos for the equipment in question will be prioritized higher. Finally, the course resource list is sorted according to the adjusted priority, and a recommendation list is generated for the top courses, which is displayed on the student's learning platform homepage or pushed to the student through messages.

[0031] Through the above scheme, this application can effectively integrate the students' multi-dimensional information and structured knowledge in the field of power safety, overcome the limitations of traditional recommendation methods that rely on single-dimensional information or simple classification, and realize personalized, dynamic and precise course resource recommendations for each student, thereby improving the pertinence and efficiency of students' learning, helping to timely fill the students' knowledge blind spots, and enhance the safety skills and awareness of power engineering practitioners, thereby better ensuring safe production in the power industry.

[0032] In some embodiments, the step of associating the student information with the element nodes in the pre-built structured association system includes: By parsing the static attribute information, the static attribute elements of the students are identified, and based on the identified static attribute elements, element nodes of different granularities corresponding to the static attribute elements are searched in the structured association system as a first set, and a static association relationship between the individual students and the first set is established; By analyzing dynamic information, the dynamic elements of the students are identified, and based on the identified dynamic elements, the element nodes related to the dynamic elements are searched in the structured association system as the second set, and a dynamic association relationship is established between the individual students and the relevant second set; the dynamic elements include information type, information content and information time; the dynamic association relationship includes association strength information and association timeliness information.

[0033] "Parsing static attribute information" refers to the structural processing of relatively stable information about trainees, such as extracting information such as position, department, and length of service from their profiles. "Identifying a trainee's static attribute elements" refers to determining specific attribute values ​​from the parsed static attribute information, such as the position title "Substation Operator" or the department name "Operation and Maintenance Department." These elements are fundamental descriptions of a trainee's identity. "Element nodes of varying granularity" refers to the fact that within a structured association system, nodes related to the same static attribute element can exist at different levels or degrees of detail. For example, nodes related to "Substation Operator" might include "Substation Operator Job Responsibilities" (coarse granularity), "Substation Equipment Operating Procedures" (medium granularity), and "110kV Transformer Inspection Key Points" (fine granularity). "Static association relationships" refer to the relatively long-term and stable connections established between individual trainees and these element nodes determined based on static attributes. "Parsing dynamic information" refers to the processing of real-time or recently generated, changing information about trainees, such as learning records, test scores, safety hazard feedback, and accident case studies. "Identifying students' dynamic elements" refers to extracting specific events or content from dynamic information, such as "Completing the course "High-voltage Switchgear Operation Safety", "Exam score of 90 points", "Submitting hidden danger feedback: the grounding wire of a certain equipment is loose", "Learning accident case: a fire accident in a certain substation". "Dynamic association relationship" refers to the timeliness and strength of the connection established between individual students and these element nodes determined based on dynamic elements. "Association strength information" is a numerical value that measures the closeness of the association between dynamic elements and related element nodes. For example, an accident feedback may have a higher association strength than an ordinary learning record. "Association timeliness information" is a numerical value that measures the validity period of the dynamic association relationship, reflecting the impact of the time when the dynamic element occurs on the current association relevance. For example, recent events have higher timeliness than events a long time ago.

[0034] This solution details the specific method for associating student information with element nodes in a structured association system. Its core approach is to distinguish between a student's static attribute information and dynamic information, establishing static and dynamic associations respectively, thereby more comprehensively and precisely characterizing the student's learning needs. Specifically, first, by analyzing the student's static attribute information, relatively stable and fundamental static attribute elements of the student are identified. Then, based on these identified static attribute elements, corresponding element nodes of varying granularity are searched within the pre-built structured association system as a first set, and a static association relationship is established between the individual student and the first set. This static association relationship reflects the basic security knowledge requirements that students should possess based on their basic identity and background. By searching for nodes of varying granularity, this basic association is made more flexible and accurate, providing a stable foundation for subsequent knowledge point identification. Second, by analyzing the student's dynamic information, dynamic elements that change in real time and are personalized to the student are identified. Based on these identified dynamic elements, element nodes related to the dynamic elements are searched within the structured association system as a second set, and a dynamic association relationship is established between the individual student and the relevant second set. This dynamic association can capture students' real-time learning status, weaknesses, or areas of concern, effectively complementing static associations. Dynamic factors include information type, content, and time. This means that when establishing dynamic associations, not only the associated knowledge points themselves (information content) are considered, but also the type of information source (information type) and the time of information generation (information time). Dynamic associations include information about the strength and timeliness of the associations, making dynamic associations more refined and accurate, and more accurately reflecting students' most pressing and relevant learning needs. By distinguishing between static and dynamic information and establishing dynamic associations with strength and timeliness, this solution addresses the granularity mismatch between student information and element nodes in the structured association system, as well as the accuracy of the association between student dynamic information and system nodes in the power engineering safety learning scenario. This approach, combining static attributes with dynamic information, results in a richer and more accurate mapping between individual students and element nodes in the structured association system. This provides a more solid and detailed foundation for subsequent knowledge point identification and course recommendation based on this mapping, overcoming the limitations of associations that rely solely on coarse-grained static information.

[0035] As a specific implementation, the following steps can be followed to associate student information with element nodes in a structured association system. For example, a student's static attribute information might include the position "High-Voltage Tester" and the department "Test Center." The system parses this information and identifies the static attribute elements "High-Voltage Tester" and "Test Center." Next, the system searches for nodes corresponding to "High-Voltage Tester" in the structured association system. This might include nodes such as "High-Voltage Tester Job Responsibilities" (coarse-grained), "High-Voltage Testing Technology" (medium-grained), and "Insulation Withstand Voltage Test" (fine-grained). These nodes are grouped as the first set, and a static association relationship is established between the student and these nodes. Nodes related to "Test Center," such as "Test Equipment Management" and "Test Safety Regulations," are also searched for and included in the first set, with static associations established. Next, the system parses the student's dynamic information. For example, a student recently completed a course called "Transformer Characteristic Test" and submitted a potential risk feedback regarding a test equipment failure, along with an exam score. The system identifies dynamic elements such as "Completed the course "Transformer Characteristic Test," "Possible risk feedback: Test equipment failure," and "Exam score." For the "Completed Course 'Transformer Characteristics Test'," the system searches for nodes related to "Transformer Characteristics Test" in the structured association system, such as "Transformer Test Technology" and "Test Data Analysis," as the second set. Based on the information type (learning record), the system determines the association strength calculation method and calculates the student's association strength with these nodes. Based on the information time (the time the course was completed), the association timeliness is calculated. For "Hazard Feedback: Test Equipment Failure," the system searches for nodes related to "Test Equipment Failure Handling" and "Equipment Maintenance Safety" as the second set. Based on the information type (hazard feedback), the system determines the association strength calculation method (which may be higher than the learning record) and calculates the association strength. Based on the information time (feedback time), the association timeliness is calculated. For "Exam Scores," the system searches for knowledge point nodes related to the exam content as the second set and calculates the association strength and timeliness based on the information type (exam scores) and time. Ultimately, each student establishes a static association with the nodes in the first set and a dynamic association with the nodes in the second set. Each dynamic association contains the calculated association strength and association timeliness information.

[0036] Through the aforementioned technical means, this solution effectively addresses the granularity mismatch between student information and the element nodes in the structured association system. By associating nodes of different granularities through static attributes, it provides students with comprehensive foundational knowledge associations. Furthermore, by parsing dynamic information and establishing dynamic associations that incorporate both strength and timeliness, the accuracy of the associations between individual students and system nodes is improved, more accurately reflecting the student's current learning status and actual needs. This enables a more refined and accurate mapping of individual students into the structured knowledge system, laying a solid foundation for subsequent personalized knowledge point identification and course recommendations.

[0037] In some embodiments, based on the identified dynamic elements, searching for element nodes related to the dynamic elements in the structured association system as a second set, and establishing a dynamic association relationship between the individual student and the related second set includes: According to the information content, searching for element nodes related to the information content in the structured association system as a second set; Determine, according to the information type, a method for calculating the strength of association between the individual student and each element node in the second set, and calculate the strength of association between the individual student and each element node in the second set based on the determined method of calculating the strength of association; Determine a calculation method for the timeliness of association between the individual student and each element node in the second set according to the information time, and calculate the timeliness of association between the individual student and each element node in the second set based on the determined calculation method for the timeliness of association; Based on the association strength between the individual student and each element node in the second set, as well as the association timeliness between the individual student and each element node in the second set, a dynamic association relationship is established between the individual student and the relevant second set.

[0038] The association strength calculation method refers to a rule or model that determines how to quantify the closeness of the association between a student's dynamic behavior (e.g., browsing, searching, learning, taking an exam, or simulated operation) and related element nodes based on the type of the behavior. This can be implemented using a preset weight table based on the behavior type, a function model based on the behavior frequency, or a mapping relationship based on the behavior results (e.g., test scores, operation scores). Association strength refers to a numerical value calculated using a specified association strength calculation method that reflects the closeness of the association between an individual student and a specific element node. This value can be a real number within a specific range, with larger values ​​indicating a closer association. The association timeliness calculation method refers to a rule or model that determines how to quantify the ongoing effectiveness of a student's dynamic behavior on the current association relationship based on the time it occurs. This can be implemented using a decay function based on time intervals (e.g., linear decay, exponential decay), a reinforcement factor based on specific events (e.g., procedure updates, accidents), or different timeliness periods based on the behavior type. Association timeliness refers to a value calculated according to a determined association timeliness calculation method, which reflects the effectiveness or urgency of the association between an individual student and a specific element node. This value can be a real number within a specific range. The larger the value, the higher or more urgent the timeliness.

[0039] The above-mentioned scheme of the present application can achieve the following working principle through the synergy of each step: First, by analyzing the specific information content of the student's dynamic behavior, the set of element nodes related to the content is accurately found and determined in the pre-built structured association system as the second set. This ensures that the dynamic association relationship established subsequently is based on the actual behavior content of the student. Then, based on the information type of the dynamic element, the system can intelligently select or determine the method for calculating the association strength between the individual student and each element node in the second set, and calculate the specific association strength value based on this. Different behavior types naturally reflect the differences in the student's attention to the relevant content, learning depth or mastery level. For example, an active search behavior may have a higher association strength than a passive browsing behavior, and passing an exam may have a higher association strength than completing a study. By distinguishing the information type to calculate the association strength, the established dynamic association relationship can more accurately reflect the student's status in knowledge or skills. At the same time, based on the information time of the dynamic element, the system can determine the method for calculating the association timeliness between the individual student and each element node in the second set, and calculate the specific association timeliness value based on this. The time of a student's behavior is a direct indicator of their current interests and needs. Recent behavior typically better reflects a student's current dynamic changes and urgent needs than more distant behavior, especially for time-sensitive knowledge in the field of power safety (such as the latest regulations and recent incidents). By considering information time to calculate association timeliness, the established dynamic association relationships can reflect the effects of time decay or intensification, prioritizing the student's recent dynamic changes and potential risk points. Finally, by combining the calculated association strength and association timeliness, a dynamic association relationship is established between the individual student and the relevant second set. This dynamic association relationship, combining strength and timeliness, provides a more comprehensive and accurate portrayal of the student's current dynamic learning. It not only reflects the student's interest in and mastery of knowledge points (through strength), but also whether these interests or knowledge states are recent or older (through timeliness). This provides high-quality, time-sensitive input for more accurate identification of relevant safety knowledge points and recommendation of more appropriate course resources. This dynamic correlation with strength and timeliness is a further refinement and enhancement of the basic solution that only establishes correlations, making the portrayal of student portraits based on dynamic information more accurate and timely, and is especially suitable for the high requirements for information timeliness in the field of power safety.

[0040] In order to more clearly illustrate the implementation method of the present application, a specific example is described below: Suppose a student completed an online exam on "Substation Switching Operation Risk Analysis" on the platform, with a score of 60 points (out of 100 points), and the exam was completed at 10:00 this morning. The system identifies the dynamic element, whose information type is "exam", the information content is "Substation Switching Operation Risk Analysis, score 60 points", and the information time is "10:00 this morning". First, based on the information content "Substation Switching Operation Risk Analysis", the system searches for element nodes related to this content in the structured association system, such as "Substation", "Switching Operation", "Risk Analysis", "Operating Procedures", "Accident Cases", etc., and uses these nodes as the second set. Then, based on the information type "exam" and "score 60 points", the system determines the association strength calculation method. For example, the preset rule may be: the association strength of the exam-type behavior is negatively correlated with the exam score, or positively correlated with the number of knowledge points that have not been mastered. Assume that based on the score calculation, the strength of the association between the student and nodes such as "substation," "switching operation," and "risk analysis" is calculated to be 0.4 (range 0-1, 1 being the strongest). At the same time, based on the information time "10 a.m. today," the system determines the calculation method for the association timeliness. For example, the preset rule may be: the timeliness factor of the behavior occurring on the same day is 1.0, and it decays by 0.1 every day. Since the behavior occurred today, the timeliness factor is calculated as 1.0. Finally, the system combines the calculated association strength of 0.4 with the association timeliness of 1.0 to establish a dynamic association relationship between the individual student and each element node in the second set, such as "substation," "switching operation," and "risk analysis." This association relationship can be stored as a record, for example, containing the student ID, element node ID, association strength value, association timeliness value, and update timestamp.

[0041] Through the above technical solution, the present application can achieve the following technical effects: by searching for relevant element nodes according to the information content, it is ensured that the basis for establishing dynamic association relationships is the content that the students actually pay attention to or are exposed to. By determining the association strength calculation method according to the information type and calculating the strength, the established dynamic association relationship can reflect the differences in the students' attention level or mastery level of the relevant content. By determining the association timeliness calculation method according to the information time and calculating the timeliness, the established dynamic association relationship can reflect the time value of the students' behavior and give priority to reflecting the students' recent dynamic changes and urgent needs. By combining the association strength and the association timeliness to establish a dynamic association relationship, the current dynamic learning portrait of the students can be portrayed more comprehensively and accurately, especially the time value of the information can be reflected, so that the knowledge points related to the recent behavior can be given a higher timeliness weight, thereby obtaining a higher priority in subsequent recommendations, improving the accuracy and timeliness of the recommendations, and helping students to pay attention to and learn the latest security knowledge that is most relevant to their current status in a timely manner, reducing potential security risks.

[0042] In some embodiments, the step of identifying a set of safety knowledge points related to the student by traversing the association path in the structured association system according to the corresponding node associated with the student includes: Determine the traversal strategy parameters for the structured association system based on the student's static attribute information; the traversal strategy parameters include the traversal priority of different association relationship types and the weight of different element node types; Based on the static association relationship established between individual students and element nodes in the structured association system, starting from the element node associated with the individual student, the association path in the structured association system is traversed according to the determined traversal strategy parameters; During the traversal process, the degree of correlation between the element nodes and the individual learners is evaluated based on the type of element nodes visited, the type of associated paths, and the traversal strategy parameters; Based on the degree of relevance of the assessment, identify the set of safety knowledge points that are relevant to the individual learner.

[0043] Static student attribute information refers to the relatively stable and unchanging personal characteristics of students registered on the learning platform or entered by administrators. This information can be represented by job title, department, type of work, region, equipment type, and years of experience. A structured association system abstracts various types of information in the field of power safety, such as safety regulations, equipment models, operating environments, risk types, accident cases, and safety knowledge points, into element nodes and establishes relationships between these nodes to form a graph structure. This structure can be constructed and stored in a knowledge graph, semantic network, or relational database. Traversal strategy parameters refer to the set of rules used to guide traversal direction and assess node importance when traversing the structured association system. They can be represented by a mapping table from association type to priority values ​​and a mapping table from element node type to weight values. Association type refers to the category of the edge connecting different element nodes in the structured association system. It can be distinguished by predefined types such as "belongs to," "involved," "may lead to," "preventive measures are," and "related equipment is." Element node types refer to the classification of different nodes in a structured association system. They can be distinguished using predefined categories such as "safety regulations," "equipment," "working environment," "risk," "knowledge point," and "accident case." Traversal priority refers to the degree to which different types of associations are prioritized or assigned a higher exploration weight during the traversal process. This can be represented by a numerical value, with larger values ​​indicating higher priority. Weight refers to the importance or influence of different element node types when assessing their relevance to learners. This can be represented by a numerical value, with larger values ​​indicating higher weights. Static association relationships refer to relatively fixed connections between individual learners and certain element nodes in the structured association system, based on their static attributes. This can be implemented by storing a correspondence between learner IDs and association node IDs in a database. An association path refers to a sequence of element nodes in a structured association system connected by association relationships. The degree of relevance refers to the degree of close association between element nodes in the structured association system and individual learners. This can be quantified using a calculated value, with larger values ​​indicating higher relevance.

[0044] This solution addresses the challenge of identifying personalized knowledge points within a complex knowledge system by introducing a traversal strategy based on the student's static attributes. First, based on the student's static attribute information, the system generates a customized set of traversal strategy parameters that reflect the student's focus on knowledge points based on factors such as their job role and environment. For example, for personnel working at heights, relationships and node types related to "risks of working at heights" and "safety belt use" are assigned higher priority or weight. Next, based on the student's established static associations with the knowledge system, the system performs a directed traversal according to these customized strategy parameters. This traversal method eliminates a blind exploration of the entire graph and prioritizes paths that are highly correlated with the student's static attributes. At each traversal step, the system dynamically calculates the relevance of the current element node to the individual student, combining the currently visited node type, the associated path type traversed, and the preset strategy parameters. This evaluation process ensures that every relevant element encountered during the traversal is quantitatively measured. Finally, based on these assessed relevance levels, the system selects safety knowledge points whose relevance meets a certain threshold, thereby forming a set of knowledge points that is highly aligned with the student's individual needs. In this way, this solution effectively integrates the student's static attribute information into the knowledge system traversal and recognition process, making the identified knowledge point set more accurate and personalized, and avoiding the interference of a large amount of irrelevant information. This traversal strategy based on static attribute guidance combined with the student's static association starting point makes the knowledge point recognition process more targeted and efficient.

[0045] For example, suppose a trainee's static attribute information indicates their position is "Transmission Line Inspector," and their work environment involves "field" and "height." The system determines traversal strategy parameters based on these static attributes. For example, it sets the traversal priority for relationships with "Risks Involved" and "Required Skills" to high, and sets the weights for feature nodes with "Work Environment," "Equipment Type," and "Risk Type" to high. Based on the static association established between the trainee and the "Transmission Line Inspector" feature node, the system begins traversal from that node. During the traversal, if it encounters the "Height Fall Risk" node connected by the "Risks Involved" relationship, the system will assess its relevance to the trainee due to its high priority and high node weight. If it further connects to the "Proper Use of Safety Belts" knowledge point node via the "Preventive Measures Are" relationship, the system will assess its relevance to the trainee based on the priorities and weights along the path. In contrast, if the traversal reaches a node related to "Substation Operating Procedures" connected by a lower-priority relationship, its relevance assessment will be lower. Finally, based on these evaluation values, the system identifies a collection of safety knowledge points that are highly relevant to the student, such as "safety belt usage specifications", "prevention of snake and insect bites", and "emergency handling for high-altitude operations".

[0046] By determining traversal strategy parameters for the structured association system based on the student's static attribute information and performing targeted traversal and relevance assessment based on these strategy parameters, this solution can identify a set of safety knowledge points that are highly relevant to the individual student from within the complex power safety knowledge system. This solves the problem of traditional methods' difficulty in accurately identifying knowledge points based on the student's specific attributes, improving the accuracy and relevance of knowledge point identification. This allows students to be provided with personalized learning content that better aligns with their job responsibilities and risk scenarios, enhancing learning efficiency and relevance.

[0047] In some embodiments, the step of identifying a set of safety knowledge points related to the student by traversing the association path in the structured association system according to the corresponding node associated with the student includes: Obtain information about the learner's experience level; Determine the traversal strategy parameters for the structured association system based on the student's static attribute information and the student's experience level information; the traversal strategy parameters include the traversal priority of different association types and the weight of different element node types; Based on the static association relationship established between individual students and element nodes in the structured association system, starting from the element node associated with the individual student, the association path in the structured association system is traversed according to the determined traversal strategy parameters; During the traversal process, the relevance between the element nodes and the individual students is evaluated based on the type of element nodes visited, the type of associated paths, the traversal strategy parameters, and the experience level of the students; Based on the assessed relevance and the trainee's experience level information, a set of safety knowledge points related to the individual trainee is identified, so that the granularity of the safety knowledge point set matches the trainee's experience level.

[0048] Experience level information refers to data reflecting a trainee's knowledge, skill proficiency, or career development stage in the field of power engineering safety. This information can be implemented using the trainee's length of service, professional title, job level, professional certifications, historical training records, assessment scores, or experience level assessment results conducted through the platform. Traversal strategy parameters refer to a set of rules or values ​​used to guide the traversal of a structured association system. This information can be implemented using a preset parameter table, parameters dynamically calculated based on a machine learning model, or parameters set based on expert experience. Traversal priorities for different association types refer to assigning different priority access orders or weights to various associations connecting element nodes (e.g., "belongs to," "related to," "is a component," "is prerequisite knowledge," etc.) during the traversal process. This information can be implemented using numerical weights, a sorted list, or a rule-based dynamic adjustment mechanism. Weights for different element node types refer to assigning different importance or access preference values ​​to different types of element nodes in the structured association system (e.g., "position," "equipment," "operating procedures," "accident cases," "knowledge points," etc.). This information can be implemented using a fixed weight table, weights dynamically adjusted based on context, or weights calculated based on node attributes. Evaluating the relevance of element nodes to individual learners refers to calculating the degree of relevance between an element node in a structured association system and the learning needs or interests of a specific learner. This can be achieved using a calculation method based on path length and weight, a calculation method based on semantic similarity, or a calculation model that combines the learner's historical behavior data. Matching the granularity of the security knowledge point set to the learner's experience level means that the level of detail, depth, and breadth of knowledge contained in the identified security knowledge point set is appropriate to the learner's current experience level. For example, basic and general knowledge points may be recommended to less experienced learners, while in-depth and specific knowledge points may be recommended to experienced learners. This can be achieved by filtering knowledge points based on experience level thresholds, adjusting the relevance assessment model based on experience level, or hierarchically expanding or aggregating knowledge points based on experience level.

[0049] When identifying a set of security knowledge points relevant to a student, this solution first obtains the student's experience level information, which reflects the student's current level of knowledge and learning stage. Then, when determining the traversal strategy parameters for the structured association system, it considers not only the student's static attribute information but also their experience level information. This means that for students with different experience levels, even if their static attributes are the same, the strategy used to traverse the association system will be adjusted, affecting the scope and focus of the traversal. Next, based on the static association relationship established between the individual student and the system, the structured association system is traversed starting from the associated nodes, according to the traversal strategy parameters determined based on their experience level. During the traversal process, when evaluating the relevance of the visited element nodes to the individual student, in addition to considering the node and path types and traversal strategy parameters, the student's experience level information is also explicitly incorporated. This enables more refined relevance assessment, enabling differentiation of the degree of need for the same knowledge point among students of different experience levels. Finally, when identifying a set of security knowledge points based on the assessed relevance, the student's experience level information is again incorporated. The key is to ensure that the granularity of the identified security knowledge point set matches the student's experience level. For example, for less experienced students, more basic and general knowledge points may be identified; for experienced students, more in-depth and professional knowledge points may be identified. By comprehensively considering the students' experience level in the process of traversal strategy determination, relevance evaluation, and final knowledge point identification, this solution can more accurately identify security knowledge points that are suitable for the students' current learning needs and cognitive levels, thereby improving the effectiveness of recommendations and the students' learning efficiency. This method introduces the key dimension of student experience level on the basis of basic static attribute-based knowledge point identification, making the knowledge point identification process more intelligent and personalized, and can effectively solve the problem of mismatched knowledge demand granularity among students with different experience levels, thereby providing a more accurate knowledge foundation for subsequent course resource recommendations.

[0050] For example, suppose a trainee's static attribute information indicates their position is "Substation Operator." If the trainee's experience level information indicates "Junior Operator," the system obtains this experience level information. When determining traversal strategy parameters, the system combines the static attribute "Substation Operator" with the experience level of "Junior" to set traversal strategy parameters. For example, the system prioritizes association paths leading to nodes related to basic operating procedures and general safety knowledge, while prioritizing association paths leading to nodes related to complex equipment troubleshooting and advanced emergency plans. The system also reduces the weight of complex equipment nodes. Starting from the "Substation Operator" node associated with the trainee, the system traverses the structured association system based on these parameters. During the traversal process, when the "Transformer Operation Safety Regulations" node is accessed, the system evaluates its relevance based on its node type, association path type, traversal strategy parameters, and the trainee's "Junior" experience level. The evaluation result may indicate that the node is highly relevant, but for a junior trainee, the focus is on basic operations. When accessing the "Transformer Fault Diagnosis and Handling" node, the evaluation results may indicate low relevance or require more basic prerequisite knowledge. Ultimately, based on the assessed relevance and combined with the "beginner" experience level, the system identifies a set of safety knowledge points primarily consisting of more fundamental knowledge points such as "Basic Substation Safety Regulations," "Basic Points for Switching Operations," and "Safety Operation Specifications for Common Equipment." Conversely, if the trainee's experience level indicates "senior operator," the system will incorporate this experience level. When determining traversal strategy parameters, the system combines the "substation operator" and "senior" experience levels to set different traversal strategy parameters. For example, it will prioritize paths leading to complex equipment fault handling and advanced emergency response plan nodes, increasing the weight of complex equipment nodes. Starting from the "substation operator" node, the system traverses based on these new parameters. During the traversal process, when accessing the "transformer operation safety regulations" node, the relevance assessment takes into account that advanced trainees may need to understand more advanced principles or handle special situations. When accessing the "Transformer Fault Diagnosis and Handling" node, the evaluation results may indicate that it is highly relevant and matches the needs of advanced learners. Ultimately, based on the assessed relevance and combined with the "Advanced" experience level, the system identifies a set of safety knowledge points that primarily include more granular knowledge points such as "Advanced Operation and Maintenance of Specific Transformer Models," "Complex Failure Mode Analysis and Emergency Response," and "Substation Risk Assessment and Management." In this way, the system can dynamically adjust the focus and depth of knowledge point identification based on the learner's experience level, ensuring that the identified knowledge point set better meets the learner's current learning needs.

[0051] By acquiring information about the student's experience level and incorporating it into the determination of traversal strategy parameters, the evaluation of element node relevance, and the final identification of the security knowledge point set, this solution can dynamically adjust the granularity of the identified security knowledge point set based on the student's actual experience level. This makes it possible to recommend basic, general knowledge points to less experienced students, and more in-depth, specific knowledge points to experienced students. This effectively addresses the mismatch in the granularity of security knowledge needs among students of different experience levels and improves the accuracy and applicability of the identified security knowledge point set.

[0052] In some embodiments, the step of adjusting the recommendation priority of course resources associated with the set of safety knowledge points based on the dynamic information of the learner, and obtaining the adjusted recommendation priority includes: Obtain course resource information associated with the security knowledge point set; According to the information type of dynamic elements, determine the basic impact weight of dynamic elements on relevant course resources; According to the information content of dynamic elements, the degree of relevance between the information content and relevant course resources is evaluated, and the preliminary impact value is calculated based on the basic impact weight; According to the time information of the dynamic elements, the time-effectiveness attenuation factor of the dynamic elements on the preliminary impact value is calculated; Combine the preliminary impact value with the time-effectiveness attenuation factor to obtain the final impact value of the dynamic factors on the relevant course resources; For multiple dynamic elements associated with the same course resource, the final impact values ​​of multiple dynamic elements are comprehensively considered, and the comprehensive priority adjustment value of the course resource is calculated according to the preset comprehensive rules; The recommendation priority of the course resources associated with the security knowledge point set is adjusted using the comprehensive priority adjustment value to obtain the adjusted recommendation priority.

[0053] The information type of a dynamic element refers to the category to which a student's dynamic information belongs, such as learning behavior records, assessment results, procedure and standard update notifications, and accident case feedback. This can be achieved using pre-set classification labels or by extracting category information from text using natural language processing techniques. The basic influence weight refers to the preset influence of different types of dynamic information on the recommended priority of course resources. This can be achieved using fixed values ​​set by expert experience, weights derived from statistical analysis of historical data, or values ​​trained through machine learning models. Information content refers to the specific data contained in dynamic information, such as specific assessment scores, procedure numbers and versions, and accident descriptions. This can be presented as structured data fields or unstructured text. The degree of relevance refers to the degree of relevance between the information content and a specific course resource in terms of topic, scope, or details. This can be achieved through keyword matching, semantic similarity calculation, ontology-based reasoning, or manual rule mapping. The preliminary impact value is the initial impact assessment of a single dynamic element on the relevant course resource, without considering time factors. This can be calculated as the product of the basic influence weight and the degree of relevance, or as a function of the relationship. Time information refers to the timestamp of the occurrence or recording of a dynamic event, which can be recorded in a standard date and time format. The time decay factor refers to the coefficient by which the influence of a dynamic factor decreases over time. It can be calculated using a linear decay function, exponential decay function, or piecewise function based on time differences. The final impact value refers to the actual impact assessment of a single dynamic factor on the relevant course resource after accounting for time decay. It can be calculated by multiplying the preliminary impact value and the time decay factor. The preset comprehensive rule refers to the logic or algorithm used to integrate the influence of multiple dynamic factors on the same course resource. It can be implemented using weighted summation, rule-based decision trees, priority sorting, or more complex machine learning models. The comprehensive priority adjustment value refers to the overall adjustment in priority that a specific course resource should receive due to the combined effect of multiple dynamic factors. It can be calculated by applying the comprehensive rule to multiple final impact values. The adjusted recommended priority refers to the final priority obtained by adding the comprehensive priority adjustment value to the original recommended priority. It can be calculated using simple numerical addition or a more complex priority mapping function.

[0054] This solution identifies the course resources associated with the student's security knowledge set by obtaining information about the course resources that require priority adjustment. Next, for each student's dynamic information, a basic impact weight is determined based on its information type. This weight reflects the varying significance of different types of events (e.g., exam failure, procedure update) for learning needs. The dynamic information's content is then analyzed to assess its relevance to specific course resources. This content relevance is combined with the basic weight of the information type to calculate a preliminary impact value, demonstrating the effective utilization of the dynamic information content. Considering that the influence of dynamic information decays over time, the solution further calculates a timeliness attenuation factor based on the time of the dynamic information and applies this factor to the preliminary impact value to obtain a final impact value that accounts for timeliness. Since a student may have multiple dynamic information items related to the same course, the solution provides a mechanism to comprehensively consider the final impact values ​​of these individual dynamic elements and, based on pre-defined rules, calculate the overall priority adjustment for the course resource. Finally, the calculated comprehensive priority adjustment is applied to the original priority of the course resource, resulting in a recommended priority that reflects the student's most current and pressing needs. By breaking down the impact of dynamic information into a comprehensive consideration of type, content, time, and multiple factors, and applying it to the student-related course resources identified in the previous steps, this solution can overcome the shortcomings of simply processing dynamic information, achieve refined and dynamic adjustment of course recommendation priorities, and make the final recommendation results more in line with the students' actual situation and needs.

[0055] For example, suppose student Xiao Wang recently has two dynamic pieces of information related to course resources related to "Safety Regulations for Working at Heights": one is that he failed an online assessment on the regulations three months ago, scoring 40 points; the other is that the latest revised version of the regulations was released last week. The system first retrieves course resource information related to "Safety Regulations for Working at Heights," such as the course "Interpretation of the New Version of Safety Regulations for Working at Heights." For the dynamic element regarding the failed assessment, the information type is "Assessment Result (Negative)," the content is "Score 40," and the time information is "Three Months Ago." Based on the "Assessment Result (Negative)" type, the system assigns a high negative base impact weight, such as -0.8. Based on the "Score 40," the system assesses its relevance to the course "Interpretation of the New Version of Safety Regulations for Working at Heights." For example, the difference between the score and the passing score indicates a high degree of relevance, and calculates a preliminary impact value, such as -0.8 * 0.9 = -0.72. Based on the time information "Three Months Ago," the system calculates a time-sensitive decay factor, such as 0.5 (indicating that the impact is halved after three months). Combining the preliminary impact value with the timeliness attenuation factor yields the final impact value for this dynamic assessment element: -0.72 * 0.5 = -0.36. For the dynamic element of the regulation revision, the information type is "Regulation Update (Important)," the content is "New Version of the Safety Regulations for High-Above-Head Work," and the time information is "Last Week." Based on the "Regulation Update (Important)" type, the system assigns a high positive base impact weight, such as +1.0. Based on the correlation between the "New Version of the Safety Regulations for High-Above-Head Work" and the course "Interpretation of the New Version of the Safety Regulations for High-Above-Head Work," the correlation is extremely high, resulting in a preliminary impact value of, for example, +1.0 * 1.0 = +1.0. Based on the time information of "Last Week," a high timeliness attenuation factor is calculated, such as 0.95 (indicating that it occurred last week and has minimal impact attenuation). Combining the preliminary impact value with the timeliness attenuation factor yields the final impact value for this dynamic element of the regulation update: +1.0 * 0.95 = +0.95. For the course "Interpretation of the New Version of the Safety Regulations for Working at Heights," there are two related dynamic elements. The system comprehensively considers the two final impact values ​​of -0.36 and +0.95 based on preset comprehensive rules (for example, recent important procedure updates take precedence over older assessment results, or a weighted sum is used, with recent events having a higher weight). If the weighted sum rule is used, and recent events have a higher weight, the calculated comprehensive priority adjustment value is, for example, 0.95*0.7+(-0.36)*0.3=0.665-0.108=+0.557. Finally, using this comprehensive priority adjustment value of +0.557, the original recommended priority of the course "Interpretation of the New Version of the Safety Regulations for Working at Heights" is adjusted to obtain the adjusted recommended priority.

[0056] Through the aforementioned technical means, this solution meticulously analyzes all types of student dynamic information, including its nature, content relevance, and timing, and provides a mechanism to comprehensively address the impact of multiple dynamic factors on the same course, even if these factors may appear contradictory. This enables the system to more accurately assess students' current real learning needs and knowledge weaknesses, and in particular, to promptly respond to important and time-sensitive events such as program updates. This allows the system to generate more personalized, dynamic, and accurate course recommendations, effectively resolving the issue of inaccurate recommendations resulting from simplistic processing of dynamic information.

[0057] Reference Attachment Figure 2 The present invention provides an intelligent recommendation system for course resources of a power engineering safety learning platform, comprising: The collection module 100 is used to collect student information; the student information includes the student's dynamic information; The association module 200 is used to associate student information with element nodes in a pre-built structured association system; the structured association system includes multiple power safety-related element nodes and association paths formed by connecting different element nodes according to specific association relationships; Identification module 300, for identifying a set of safety knowledge points related to the student by traversing the association path in the structured association system based on the corresponding nodes associated with the student; An adjustment module 400 is configured to adjust the recommendation priority of course resources associated with the safety knowledge point set based on the student's dynamic information to obtain an adjusted recommendation priority; The generation module 500 is used to screen and sort the course resources according to the adjusted recommendation priority, generate a recommendation list and push it to the students.

[0058] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0059] The foregoing description is merely an embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An intelligent recommendation method for course resources on a power engineering safety learning platform, characterized in that: The following steps are involved: Collect student information; student information includes student dynamic information; Establish associations between student information and element nodes in a pre-built structured association system; the structured association system includes multiple element nodes related to power safety and association paths formed by connecting different element nodes according to specific association relationships; According to the corresponding nodes associated with the students, the set of safety knowledge points related to the students is identified by traversing the association paths in the structured association system; According to the dynamic information of the students, the recommendation priority of the course resources associated with the security knowledge point set is adjusted to obtain the adjusted recommendation priority; Based on the adjusted recommendation priority, the course resources are filtered and sorted, and a recommendation list is generated and pushed to the students.

2. The intelligent recommendation method for course resources of the electric power engineering safety learning platform according to claim 1 is characterized in that: The student information also includes the student's static attribute information.

3. The intelligent recommendation method for course resources of the electric power engineering safety learning platform according to claim 2 is characterized in that: The steps for associating student information with element nodes in the pre-built structured association system include: By parsing the static attribute information, the static attribute elements of the students are identified, and based on the identified static attribute elements, element nodes of different granularities corresponding to the static attribute elements are searched in the structured association system as a first set, and a static association relationship between the individual students and the first set is established; By analyzing dynamic information, the dynamic elements of the students are identified, and based on the identified dynamic elements, the element nodes related to the dynamic elements are searched in the structured association system as the second set, and a dynamic association relationship is established between the individual students and the relevant second set; the dynamic association relationship includes association strength information and association timeliness information.

4. The intelligent recommendation method for course resources of the electric power engineering safety learning platform according to claim 3 is characterized in that: Dynamic elements include information type, information content and information time.

5. The method for intelligently recommending course resources for a power engineering safety learning platform according to claim 4 is characterized in that: According to the identified dynamic elements, searching for element nodes related to the dynamic elements in the structured association system as a second set, and establishing a dynamic association relationship between the individual student and the related second set includes the following steps: According to the information content, searching for element nodes related to the information content in the structured association system as a second set; Determine, according to the information type, a method for calculating the strength of association between the individual student and each element node in the second set, and calculate the strength of association between the individual student and each element node in the second set based on the determined method of calculating the strength of association; Determine a calculation method for the timeliness of association between the individual student and each element node in the second set according to the information time, and calculate the timeliness of association between the individual student and each element node in the second set based on the determined calculation method for the timeliness of association; Based on the association strength between the individual student and each element node in the second set, as well as the association timeliness between the individual student and each element node in the second set, a dynamic association relationship is established between the individual student and the relevant second set.

6. The method for intelligently recommending course resources for a power engineering safety learning platform according to claim 3 is characterized in that: The steps of identifying a set of safety knowledge points related to the trainee by traversing the association paths in the structured association system according to the corresponding nodes associated with the trainee include: Determine the traversal strategy parameters for the structured association system based on the student's static attribute information; Based on the static association relationship established between individual students and element nodes in the structured association system, starting from the element node associated with the individual student, the association path in the structured association system is traversed according to the determined traversal strategy parameters; During the traversal process, the degree of correlation between the element nodes and the individual learners is evaluated based on the type of element nodes visited, the type of associated paths, and the traversal strategy parameters; Based on the degree of relevance of the assessment, identify the set of safety knowledge points that are relevant to the individual learner.

7. The method for intelligently recommending course resources for a power engineering safety learning platform according to claim 3, characterized in that: The steps of identifying a set of safety knowledge points related to the trainee by traversing the association paths in the structured association system according to the corresponding nodes associated with the trainee include: Obtain information about the learner's experience level; Determine the traversal strategy parameters for the structured association system based on the student's static attribute information and the student's experience level information; Based on the static association relationship established between individual students and element nodes in the structured association system, starting from the element node associated with the individual student, the association path in the structured association system is traversed according to the determined traversal strategy parameters; During the traversal process, the relevance between the element nodes and the individual students is evaluated based on the type of element nodes visited, the type of associated paths, the traversal strategy parameters, and the experience level of the students; Based on the relevance of the assessment and the trainee's experience level information, a set of safety knowledge points relevant to the individual trainee is identified.

8. The method for intelligently recommending course resources for a power engineering safety learning platform according to claim 6 or 7, characterized in that: The traversal strategy parameters include the traversal priorities of different relationship types and the weights of different feature node types.

9. The method for intelligently recommending course resources for a power engineering safety learning platform according to claim 4, characterized in that: The recommendation priority of course resources associated with the security knowledge point set is adjusted based on the student's dynamic information. The steps for obtaining the adjusted recommendation priority include: Obtain course resource information associated with the security knowledge point set; According to the information type of dynamic elements, determine the basic impact weight of dynamic elements on relevant course resources; According to the information content of dynamic elements, the degree of relevance between the information content and relevant course resources is evaluated, and the preliminary impact value is calculated based on the basic impact weight; According to the time information of the dynamic elements, the time-effectiveness attenuation factor of the dynamic elements on the preliminary impact value is calculated; Combine the preliminary impact value with the time-effectiveness attenuation factor to obtain the final impact value of the dynamic factors on the relevant course resources; For multiple dynamic elements associated with the same course resource, the final impact values ​​of multiple dynamic elements are comprehensively considered, and the comprehensive priority adjustment value of the course resource is calculated according to the preset comprehensive rules; The recommendation priority of the course resources associated with the security knowledge point set is adjusted using the comprehensive priority adjustment value to obtain the adjusted recommendation priority.

10. An intelligent recommendation system for course resources of a power engineering safety learning platform, characterized in that: include: Collection module, used to collect student information; Student information includes student dynamic information; The association module is used to associate student information with element nodes in a pre-built structured association system; the structured association system includes multiple power safety-related element nodes and association paths formed by connecting different element nodes according to specific association relationships; The identification module is used to identify the set of safety knowledge points related to the student by traversing the association path in the structured association system based on the corresponding nodes associated with the student; An adjustment module, configured to adjust the recommendation priority of course resources associated with the security knowledge point set according to the dynamic information of the students, and obtain an adjusted recommendation priority; The generation module is used to filter and sort course resources according to the adjusted recommendation priority, generate a recommendation list and push it to students.

Images